DEV Community

Kelly Andrews for Vonage

Posted on • Originally published at nexmo.com on

Translating SMS Messages Using Google Cloud’s Translation API

Text messaging has become a part of our daily lives. We integrate it into multiple aspects like banking, alerts, marketing, and support. It has become simple to implement, and Nexmo is no different.

As a part of the Extend team here, integrating text messages with translation API’s makes perfect sense. Translating incoming text messages can help break down communication barriers and help you reach a broader audience.

Overview

In this post, I show you how to create an inbound Nexmo SMS webhook and translate the message into English using the Google Cloud Translation API.

In order to get started, you will need the following items setup:

Create Your Project

The setup for this example is minimal, and you only need a couple of packages to get going.

  • @google-cloud/translate – this is the official Cloud Translation SDK
  • express – web framework to serve the webhook
  • dotenv – a package to load environment variables
  • body-parser – middleware for Express to handle the incoming webhook object

Initialize the project and then install the above requirements using npm or yarn.

npm init && npm install @google-cloud/translate express dotenv body-parser
# or
yarn init && yarn add @google-cloud/translate express dotenv body-parser
Enter fullscreen mode Exit fullscreen mode

Once installed, create an index.js and .env file.

touch index.js .env
Enter fullscreen mode Exit fullscreen mode

Open up the .env file first, adn copy and paste the following:

GOOGLE_APPLICATION_CREDENTIALS=./google_creds.json
TARGET_LANGUAGE='en'
Enter fullscreen mode Exit fullscreen mode

Next, open the index.js file and put the following code inside:

'use strict';
require('dotenv').config();

const express = require('express');
const bodyParser = require('body-parser');
const { Translate } = require('@google-cloud/translate');

const app = express();

app.use(bodyParser.json());
app.use(bodyParser.urlencoded({ extended: true }));

const server = app.listen(3000, () => {
  console.log(`Express server listening on port ${server.address().port} in ${app.settings.env} mode`);
});
Enter fullscreen mode Exit fullscreen mode

This will set up the server to run the example.

Installing Ngrok

Webhooks need to be publicly available so that the Nexmo service can reach the application when incoming SMS messages are received. You could push your code up to a publicly available server, or you can use ngrok to allow for public traffic to reach your local application.

You can learn more about installing ngrok with this post. After you have everything ready to go you can start ngrok using the following command to create your tunnel.

ngrok http 3000
Enter fullscreen mode Exit fullscreen mode

Make a note of the ngrok address, as you will need that in a later step.

Setting Up Google Cloud Translation API

Once you have the initial items set up, you can now add Google Cloud Translation API to your account. Follow this link to enable the Translation API. Select a project, and then click the Enable button to activate the API on that project.

Enable Google Cloud Translation API

It is recommended to create a service user that has access to the Translation API. Click here and click + Create Service Account.

Add New Service Account

Give the account any name you’d like, and press the Create button. After the account is created, add the Cloud Translation API User role, and click Continue.

Add Cloud Translation API User Role

You will need to create keys for this user. Go ahead and click the + Create Key button, and then select JSON and click create. This will download a JSON file to your machine that you will need to use the account. When that is completed, click Done to complete the creation process.

Create Service Account Key

Create Service Account Key - Select Type

Copy the credentials file into your project folder:

cp /path/to/file/project-name-id.json ./google\_creds.json
Enter fullscreen mode Exit fullscreen mode

The Google Cloud Translation API is now set up and ready to use.

Next, we can set up the phone number.

Setting Up Nexmo Inbound SMS Messages

This example requires a phone number from Nexmo to receive inbound messages. We can do this by using the Nexmo CLI right from a terminal.

Purchase a Virtual Phone Number

The first step will be to purchase a number (feel free to use a different ISO 3166 alpha-2 country code as needed).

nexmo number:buy --country\_code US
Enter fullscreen mode Exit fullscreen mode

Although the actual route to use in the application isn’t set up, you will name it /message. The phone number needs to be linked to this route so inbound messages know where to go. Get the ngrok host name from the previous setup and use it here:

nexmo link:sms phone\_number https://my-ngrok-hostname/message
Enter fullscreen mode Exit fullscreen mode

Now we have the Nexmo webhook set up as a place for inbound SMS messages to be routed.

Finish the Application

All that is left for this tutorial is creating the Express route to handle the incoming data and a couple of small functions to actually perform the translation.

Build the Webhook

First, we need to build the webhook code. Nexmo has a built in feature for setting default SMS behaviour. In the settings panel you can change the default HTTP method used. Mine is set to POST-JSON. I would recommend using this setting if possible, however the code used in this example will handle all three options in case you are unable to modify this setting.

Default Nexmo SMS HTTP Method

Open up the index.js file, and at the bottom, paste the following code:

// Reading the inbound SMS messages
const handleRoute = (req, res) => {

  let params = req.body;

  if (req.method === "GET") {
    params = req.query
  }

  if (!params.to || !params.msisdn) {
    res.status(400).send({'error': 'This is not a valid inbound SMS message!'});
  } else {
    translateText(params);
    res.status(200).end();
  }

};
Enter fullscreen mode Exit fullscreen mode

The above snippet is the method we will pass into the routes. If the incoming message is using POST it will use req.body, and it will use req.query for the GET option. As long as the inbound payload is properly set up, the object will be sent along to the translateText method to display the translation.

Now you can add the route and proper HTTP methods to the application.

app.route('/message')
  .get(handleRoute)
  .post(handleRoute)
  .all((req, res) => res.status(405).send());
Enter fullscreen mode Exit fullscreen mode

The above code will create the GET and POST methods to handle either from the inbound SMS webhook message. If any other method is used, a 405 - Method Not Allowed response will be returned.

The webhook is ready to go and the final piece is the actual translations.

Translation Method

In the previous step we call translateText. This step will create that method.

Using the @google-cloud/translate package is really straight forward. We first instantiate the Translate class, which will give us the translate method. This is called within the translateText method and uses the text field from the inbound SMS message object. The target input is any two-letter code for the language to translate into.

const translationApi = new Translate();

function translateText(params) {
  const target = process.env.TARGET_LANGUAGE || 'en';

  translationApi.translate(params.text, target)
        .then(results => {
           console.log(`Original Text: ${params.text}`);
           console.log(`Translation: ${results[0]}`);
         })
         .catch(err => {
           console.log('error', err);
         });
}
Enter fullscreen mode Exit fullscreen mode

Now you can test out the functionality by starting the server, and sending a text message to the number you purchased earlier.

node index.js
# Text "Hola" to your phone number

# expected response
Original Text: Hola
Translation: Hello
Enter fullscreen mode Exit fullscreen mode

The Google Cloud Translation API does an amazing job at detecting the incoming language and processing the translation quickly. Have fun and try it out.

Recap

The example above is just a small introduction to translation, but should be a good start to get you going. From here you can translate the inbound message, and then translate the outbound message into the correct language as well (future blog post, for sure).

For a completed version of this tutorial you can find it at https://github.com/nexmo-community/sms-translate-google-js.

If you want to learn more about the Extend projects we have, you can visit https://developer.nexmo.com/extend to learn more.

The post Translating SMS Messages Using Google Cloud’s Translation API appeared first on Nexmo Developer Blog.

Top comments (0)